Added validation of VCF files in integration tests. Fixed flag InDelL…

…ikely name in expected file and duplicated Bias filter. Updated submodule.
AstraZeneca-NGS · Sep 2, 2020 · d68f42f · d68f42f
1 parent cfcb765
commit d68f42f
Show file tree

Hide file tree

Showing 4 changed files with 10 additions and 3 deletions.
diff --git a/VarDict b/VarDict
diff --git a/tests/integration/config.sh b/tests/integration/config.sh
@@ -4,6 +4,8 @@ set -o pipefail
 #---
 # Paths
 #---
+# Validation of VCF files with EBIvariation vcf-validator, must be on the PATH
+VCF_VALIDATOR="vcf_validator"
 
 WORKSPACE="$HOME/IdeaProjects"
 WORKSPACE="$HOME/workspace"

diff --git a/tests/integration/expected/vardict.paired.vcf b/tests/integration/expected/vardict.paired.vcf
@@ -15,7 +15,7 @@
 ##INFO=<ID=RSEQ,Number=1,Type=String,Description="3' flanking seq">
 ##INFO=<ID=STATUS,Number=1,Type=String,Description="Somatic or germline status">
 ##INFO=<ID=P0.01Likely,Number=0,Type=Flag,Description="Likely candidate but p-value > 0.01/5**vd2 (means the evidence in tumor sample might be weak, e.g. small diff in AF)">
-##INFO=<ID=IndelLikely,Number=0,Type=Flag,Description="Likely indels more than 2bp are not considered somatic (weak evidence of presence in normal samples)">
+##INFO=<ID=InDelLikely,Number=0,Type=Flag,Description="Likely indels more than 2bp are not considered somatic (weak evidence of presence in normal samples)">
 ##FILTER=<ID=q22.5,Description="Mean Base Quality Below 22.5">
 ##FILTER=<ID=Q0,Description="Mean Mapping Quality Below 0">
 ##FILTER=<ID=p8,Description="Mean Position in Reads Less than 8">
@@ -3141,7 +3141,7 @@
 20	33501567	.	C	A	30	v3;f0.02	STATUS=StrongSomatic;SAMPLE=abc;TYPE=SNV;DP=993;VD=2;AF=0.002;SHIFT3=0;MSI=2.000;MSILEN=2;SSF=0.4306;SOR=0;LSEQ=CTTCCCTAGTTTGCAGGCTT;RSEQ=TCTTCAGAGTCTCTATGTGA	GT:DP:VD:ALD:RD:AD:AF:BIAS:PMEAN:PSTD:QUAL:QSTD:SBF:ODDRATIO:MQ:SN:HIAF:ADJAF:NM	0/0:993:2:0,2:485,503:988,2:0.002:2,0:17:1:30.8:1:0.4997:0:60:4:0.0021:0.001:1	0/0:520:0:0,0:270,250:520,0:0:2,0:18.6:1:34.2:1:1:0:59:19.8:1:0:0.1
 20	33501572	.	C	A	49	f0.02	STATUS=StrongSomatic;SAMPLE=abc;TYPE=SNV;DP=948;VD=3;AF=0.0032;SHIFT3=0;MSI=1.000;MSILEN=1;SSF=0.27515;SOR=0;LSEQ=CTAGTTTGCAGGCTTCTCTT;RSEQ=AGAGTCTCTATGTGAACGGA	GT:DP:VD:ALD:RD:AD:AF:BIAS:PMEAN:PSTD:QUAL:QSTD:SBF:ODDRATIO:MQ:SN:HIAF:ADJAF:NM	0/0:948:3:2,1:407,538:945,3:0.0032:2,2:25:1:31:1:0.58105:2.64:60:6:0.0033:0:1	0/0:509:0:0,0:247,261:508,0:0:2,0:18.9:1:34.1:1:1:0:59:11.39:1:0:0.1
 20	33501579	.	T	A	35	f0.02	STATUS=LikelySomatic;SAMPLE=abc;TYPE=SNV;DP=928;VD=3;AF=0.0032;SHIFT3=1;MSI=2.000;MSILEN=2;SSF=0.55239;SOR=0.77206;LSEQ=GCAGGCTTCTCTTCAGAGTC;RSEQ=CTATGTGAACGGATCTTGGA	GT:DP:VD:ALD:RD:AD:AF:BIAS:PMEAN:PSTD:QUAL:QSTD:SBF:ODDRATIO:MQ:SN:HIAF:ADJAF:NM	0/0:928:3:1,2:357,566:923,3:0.0032:2,2:15.3:1:22.7:1:1:1.26115:50:2:0.0022:0:1	0/0:478:2:0,2:204,269:473,2:0.0042:2,0:15:1:17.5:1:0.50891:0:60:0:0:0:1.5
-20	33502196	.	A	C	81	Bias;Bias	STATUS=AFDiff;SAMPLE=abc;TYPE=SNV;DP=49;VD=14;AF=0.2857;SHIFT3=0;MSI=2.000;MSILEN=1;SSF=0.07586;SOR=0.47487;LSEQ=AGCTCGGCATGGGTGACTCC;RSEQ=CCAGCCAGTCCCCCCCAATT	GT:DP:VD:ALD:RD:AD:AF:BIAS:PMEAN:PSTD:QUAL:QSTD:SBF:ODDRATIO:MQ:SN:HIAF:ADJAF:NM	0/1:49:14:0,14:29,6:35,14:0.2857:2,1:10.7:1:23.7:1:0:0:33:2.5:0.25:0:4	0/1:37:17:1,16:15,5:20,17:0.4595:2,1:15.8:1:20:1:0.00003:41.60206:44:0.7:0.2692:0.1622:2.5
+20	33502196	.	A	C	81	Bias	STATUS=AFDiff;SAMPLE=abc;TYPE=SNV;DP=49;VD=14;AF=0.2857;SHIFT3=0;MSI=2.000;MSILEN=1;SSF=0.07586;SOR=0.47487;LSEQ=AGCTCGGCATGGGTGACTCC;RSEQ=CCAGCCAGTCCCCCCCAATT	GT:DP:VD:ALD:RD:AD:AF:BIAS:PMEAN:PSTD:QUAL:QSTD:SBF:ODDRATIO:MQ:SN:HIAF:ADJAF:NM	0/1:49:14:0,14:29,6:35,14:0.2857:2,1:10.7:1:23.7:1:0:0:33:2.5:0.25:0:4	0/1:37:17:1,16:15,5:20,17:0.4595:2,1:15.8:1:20:1:0.00003:41.60206:44:0.7:0.2692:0.1622:2.5
 20	33508401	.	G	T	34	v3;f0.02	STATUS=StrongSomatic;SAMPLE=abc;TYPE=SNV;DP=230;VD=2;AF=0.0087;SHIFT3=0;MSI=3.000;MSILEN=1;SSF=0.44639;SOR=0;LSEQ=GCCACAACCTTCAAGTATGT;RSEQ=TTTGACTTCCATGCAGAGGA	GT:DP:VD:ALD:RD:AD:AF:BIAS:PMEAN:PSTD:QUAL:QSTD:SBF:ODDRATIO:MQ:SN:HIAF:ADJAF:NM	0/0:230:2:1,1:106,122:228,2:0.0087:2,2:11:1:34.5:1:1:1.15:60:4:0.0091:0.0043:1	0/0:114:0:0,0:55,59:114,0:0:2,0:16:1:35.3:1:1:0:59:56:1:0:0.4
 20	33508470	.	C	A	26	v3;f0.02	STATUS=StrongLOH;SAMPLE=abc;TYPE=SNV;DP=153;VD=0;AF=0;SHIFT3=0;MSI=1.000;MSILEN=1;SSF=0.12272;SOR=0;LSEQ=TGGATCACTGGTCATTCCTA;RSEQ=GTCACCTATGGGCCACTGGC	GT:DP:VD:ALD:RD:AD:AF:BIAS:PMEAN:PSTD:QUAL:QSTD:SBF:ODDRATIO:MQ:SN:HIAF:ADJAF:NM	0/0:153:0:0,0:47,106:153,0:0:2,0:17.3:1:30.7:1:1:0:59:14.3:1:0:0.2	0/1:83:2:2,0:19,62:81,2:0.0241:2,0:13.5:1:26.8:1:0.06171:0:60:4:0.029:0.012:1.5
 20	33508814	.	G	T	27	v3;f0.02	STATUS=StrongSomatic;SAMPLE=abc;TYPE=SNV;DP=523;VD=2;AF=0.0038;SHIFT3=3;MSI=4.000;MSILEN=1;SSF=0.42181;SOR=0;LSEQ=GCCTTCATGGGTCAGTTTGA;RSEQ=GGGATTCCCACATATCCGGA	GT:DP:VD:ALD:RD:AD:AF:BIAS:PMEAN:PSTD:QUAL:QSTD:SBF:ODDRATIO:MQ:SN:HIAF:ADJAF:NM	0/0:523:2:1,1:291,230:521,2:0.0038:2,2:19.5:1:27.5:1:1:1.26464:60:4:0.0041:0:1.5	0/0:282:0:0,0:170,112:282,0:0:2,0:18:1:35.8:1:1:0:59:39.286:1:0:0.2

diff --git a/tests/integration/tests_integration.sh b/tests/integration/tests_integration.sh
@@ -1,6 +1,7 @@
 #!/bin/bash -eu
 set -o pipefail
 
+# Needs EBIvariation vcf-validator to be installed on path to validate VCF files
 #---
 # Config variables
 #---
@@ -244,6 +245,10 @@ function vcf_testing {
     echo Running paired mode VCF integration testing
     cat $RAWVARDICT_PAIRED | $VARDICTPERL_R_PAIRED | $VARDICTPERL_VAR_PAIRED > $VARDICT_VCF_PAIRED
     diff_results "VCF_paired" $VARDICT_VCF_PAIRED_EXP  $VARDICT_VCF_PAIRED
+
+    echo Running validation of VCF files
+    $VCF_VALIDATOR -i $VARDICT_VCF_SIMPLE
+    $VCF_VALIDATOR -i $VARDICT_VCF_PAIRED
 }
 
 download_files